© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 972
    Prev
    Next
    INDEX
    Explanations

    Formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.67
     vectorielles
    -0.65
     nakalista
    -0.63
    ródło
    -0.59
     étoient
    -0.58
     scattata
    -0.58
     متعلقه
    -0.57
     TextInputType
    -0.57
    tvguidetime
    -0.56
     slutet
    -0.56
    POSITIVE LOGITS
     to
    1.20
     by
    0.78
     attempt
    0.61
     amend
    0.53
     try
    0.51
    UnsafeEnabled
    0.48
     legislature
    0.48
    kloped
    0.47
    attempt
    0.46
     restore
    0.46
    Activations Density 0.001%

    No Known Activations